© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37277
    Prev
    Next
    INDEX
    Explanations

    media formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī¥ç¦»
    -0.08
    itet
    -0.08
    8
    -0.07
    ä½ļ
    -0.07
    мел
    -0.07
    pch
    -0.07
    åį¿
    -0.07
    æ¯ı个人
    -0.07
    å¹´å¤ľ
    -0.07
    æľĢåħ³éĶ®çļĦ
    -0.07
    POSITIVE LOGITS
    ijľ
    0.11
    åīįå¤ķ
    0.10
    å®Ĺ
    0.10
    翼
    0.10
    å¦ĤæľŁ
    0.10
    é¤IJ
    0.10
    ç«¥è£ħ
    0.09
    æĻĤçĤ¹ãģ§
    0.09
    åīįåĩłå¤©
    0.09
    åѦçĶŁä»¬
    0.09
    Activations Density 0.025%

    No Known Activations